Indonesia · WIB

Hi, I’m Rio.

█

Resume

Scroll Down

I build intelligent software systems at the intersection of AI, machine learning,

and product engineering. My primary focus is AI that solves real problems,

backed by reliable software systems.

I also build native iOS apps in Swift,

bringing the same care to mobile experiences and everyday workflows.

PythonPyTorchLangChainSwiftSwiftUIUIKitFlutterGoTypeScriptNext.jsReactNode.jsPostgreSQLQdrantDockerTailwind CSSPythonPyTorchLangChainSwiftSwiftUIUIKitFlutterGoTypeScriptNext.jsReactNode.jsPostgreSQLQdrantDockerTailwind CSS

Selected work / Applied AI

AI, put to work.

Three different problems. One focus: useful AI, grounded in context, connected to reliable systems, and built for people.

View all projects Explore Swift / iOS

Project 01 / Full-Stack AI Engineer

Strata PDA

Your documents. Your voice. Traceable answers.

A document assistant that turns personal archives into context-aware drafts. Local embeddings, source citations, and reusable writing personas connect AI generation to the documents and style that matter to each user.

Highlights

01Local RAG with BGE-M3 and Qdrant
02Reusable writing personas and source citations
03Streaming drafts with live preview and DOCX export

1,024

Embedding dimensions

PDF + DOCX

Document ingestion

SSE

Draft streaming

PythonFastAPIQdrantBGE-M3GeminiReact

Explore the case study

Project 02 / Full-Stack & AI Engineer

Streamly

Turn a fast-moving live chat into a clear next move.

An AI co-pilot for TikTok Live that turns chat activity into audience sentiment, emerging topics, and practical actions. Hierarchical summaries preserve the conversation's timeline across short pulses, developing trends, and session reviews.

Highlights

01Hierarchical summaries across 5, 20, and 45 minutes
02Atomic Redis batch isolation during chat ingestion
03Sentiment, emerging topics, and actionable AI insights

5 / 20 / 45m

Analysis windows

Redis

Queue + insight cache

Demo

No live stream required

TypeScriptNode.jsRedisGeminiReactExpress

Explore the case study

Signalroom market research terminal with fundamental and price discrepancy controls — 01 / 05 · Signalroom terminal
Full size
Configure a research scan and compare fundamental performance with price behavior.

Project 03 / AI & Backend Engineer

Market Intelligence

From market anomaly to an evidence-backed research memo.

Signalroom is an IDX research terminal that connects robust statistical screening, cited AI research, and deterministic scenario testing. Each research run stays tied to one market snapshot so its evidence and calculations can be revisited.

Highlights

01Robust screening with median/MAD and outlier controls
02Cited Gemini research validated with Pydantic
03Deterministic stress tests and immutable snapshot replay

357

Documented automated tests

Stress scenarios

Snapshot

Reproducible research

PythonFastAPIPydanticGeminiSectors APIpytest

Explore the case study

Native iOS / Swift · 03 projects

Built for iOS. Written in Swift.

UIKit and SwiftUI interfaces, durable uploads, local persistence, and AR experiences. Three native apps that show how I build beyond the model and into the hands of users.

Slate

From creative brief to verified file delivery.

Durable background uploads with multipart recovery

SwiftUIKitCore Data

BrandLens

Printed campaigns, brought into another dimension.

ARKit image tracking and RealityKit scenes

SwiftUIKitARKit

Personal Money Tracker

Make everyday money tracking easy to keep up with.

Quick IDR entry and dedicated Grocery tracking

SwiftSwiftUISwiftData

Cross-platform / Flutter & Web

One product. Android, iOS, and web.

Flutter & Full-Stack Engineer

Rantang

A food commerce workspace with a Flutter seller app for Android and iOS, alongside a web storefront and dashboard. Account-free buyer checkout, pre-order capacity reservations, and a seller order pipeline connect customers to kitchen operations.

Coding activity

GitHub Contributions

Open-source activity tracker showing commits, pull requests, and code reviews.

Last 365 Days

contributions in the last year

Longest Streak

0 days

Active Days

0 days

@rfirmn•Live sync · Updated weekly

LessMore

Hi, I’m Rio.

About Rio Firman Raharja, Machine Learning & Applied AI Engineer

Selected projects

Strata PDA

Streamly

Market Intelligence

Built for iOS. Written in Swift.

Slate

BrandLens

Personal Money Tracker

One product. Android, iOS, and web.

GitHub Contributions